Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4213 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1471837 (Python Code)

Max Activating Token Index: 852

Text #1

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1589037 (Python Code)

Max Activating Token Index: 883

Text #2

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1586632 (Python Code)

Max Activating Token Index: 267

Text #3

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1542295 (Python Code)

Max Activating Token Index: 163

Text #4

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1382410 (Python Code)

Max Activating Token Index: 287

Text #5

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1419057 (Python Code)

Max Activating Token Index: 131

Text #6

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1463884 (Python Code)

Max Activating Token Index: 744

Text #7

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1502852 (Python Code)

Max Activating Token Index: 297

Text #8

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1412932 (Python Code)

Max Activating Token Index: 518

Text #9

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1435712 (Python Code)

Max Activating Token Index: 735

Text #10

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1467326 (Python Code)

Max Activating Token Index: 99

Text #11

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1531579 (Python Code)

Max Activating Token Index: 196

Text #12

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1428036 (Python Code)

Max Activating Token Index: 329

Text #13

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1489742 (Python Code)

Max Activating Token Index: 270

Text #14

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1516187 (Python Code)

Max Activating Token Index: 430

Text #15

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1625089 (Python Code)

Max Activating Token Index: 194

Text #16

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1374942 (Python Code)

Max Activating Token Index: 538

Text #17

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1599239 (Python Code)

Max Activating Token Index: 390

Text #18

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1640168 (Python Code)

Max Activating Token Index: 720

Text #19

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1581986 (Python Code)

Max Activating Token Index: 20